remove cogito for gpu-hour reasons and add approved llama models

utils/models.py

@@ -10,13 +10,13 @@ from .shared import generation_interrupt
 models = {
     "Qwen2.5-1.5b-Instruct": "qwen/qwen2.5-1.5b-instruct",
     "Qwen2.5-3b-Instruct": "qwen/qwen2.5-3b-instruct",
-    #"Llama-3.2-1b-Instruct": "meta-llama/llama-3.2-1b-instruct",
-    #"Llama-3.2-3b-Instruct": "meta-llama/llama-3.2-3b-instruct",
+    "Llama-3.2-1b-Instruct": "meta-llama/llama-3.2-1b-instruct",
+    "Llama-3.2-3b-Instruct": "meta-llama/llama-3.2-3b-instruct",
     "Gemma-3-1b-it": "google/gemma-3-1b-it",
     #"Gemma-3-4b-it": "google/gemma-3-4b-it",
     "Gemma-2-2b-it": "google/gemma-2-2b-it",
     "Phi-4-mini-instruct": "microsoft/phi-4-mini-instruct",
-    "Cogito-v1-preview-llama-3b": "deepcogito/cogito-v1-preview-llama-3b",
+    #"Cogito-v1-preview-llama-3b": "deepcogito/cogito-v1-preview-llama-3b",
     "IBM Granite-3.3-2b-instruct": "ibm-granite/granite-3.3-2b-instruct",
 
 }